Sim is the open-source AI workspace where teams build, deploy, and manage AI agents. This page compares DeepSeek V4 Pro and Kimi K3 on API pricing per 1M tokens, context window, max output, and capabilities. Both models are available in the Sim Agent block, and each Agent block in a Sim agent can use a different model.
API model comparison
DeepSeek V4 Pro vs Kimi K3
DeepSeek V4 Pro is 2.6× cheaper than Kimi K3: 1,000 agent calls with 10k input and 1k output tokens each cost $17.16 versus $45 at standard rates.
DeepSeek V4 Pro charges $1.32 input and $3.96 output per 1M tokens; Kimi K3 charges $3 and $15.
Their context windows are about the same size: 1M versus 1.05M tokens.
Kimi K3 can generate up to 1.05M output tokens per response, versus 384k.
Both support configurable reasoning and tool choice control in Sim.
Pricing, context window, and capabilities
API prices are per 1M tokens. Pricing last updated .
| Metric | DeepSeek V4 Pro | Kimi K3 |
|---|---|---|
| Provider | DeepSeek | Kimi |
| Input price | $1.32/1M | $3/1M |
| Cached input | $0.044/1M | $0.3/1M |
| Output price | $3.96/1M | $15/1M |
| Context window | 1M tokens | 1.05M tokens |
| Released | Apr 24, 2026 | Jul 16, 2026 |
| Temperature | Not configurable | Not configurable |
| Reasoning effort | low, high, max | low, high, max |
| Verbosity | Not supported | Not supported |
| Thinking levels | none, enabled (default: enabled) | Not supported |
| Structured outputs | Supported | Supported |
| Tool choice | Supported | Supported |
| Computer use | Not supported | Not supported |
| Deep research | Not supported | Not supported |
| Memory support | Supported | Supported |
| Max output tokens | 384k | 1.05M |
Use DeepSeek V4 Pro or Kimi K3 in a Sim agent
Both models are available in the Sim Agent block. Pick either one from the model picker, and each Agent block in the same agent can use a different model.
Frequently asked questions
DeepSeek V4 Pro is 2.6× cheaper than Kimi K3: 1,000 agent calls with 10k input and 1k output tokens each cost $17.16 versus $45 at standard rates. DeepSeek V4 Pro charges $1.32 input and $3.96 output per 1M tokens; Kimi K3 charges $3 and $15.
